• NOW LIVE! Into the Woods--new character species, eerie monsters, and haunting villains to populate the woodlands of your D&D games.

D&D General DALL·E 3 does amazing D&D art

I've read the most recent 5-10 pages here but there are over 600 so I'm not sure I dare ask, as I assume this has been done to death, but I too am wow'd by a lot of this AI art, which seems so much better in the D&D domain than in other applications where I've seen it utilized, that said, the big question to me is what does this mean for fantasy illustrators and artists?

I am trying to understand an expressed difficulty with this Tiefling Bard.

1746399551741.png


The artwork is technically high quality. Good composition, vibrant use of color, dramatic use of lines and perspective, and so on. For my tastes, it is realistic enough for me to appreciate.

Obviously the portrait itself is appropriate for D&D fantasy, a Tiefling Bard with a medieval troubadour concept.

Exactly for the same reason than the stupid druid one. They don't depict anything heroic. The hero here is dancing and playing a merry tune on a violin on a table among a crowd of drunken people throwing roses at him. That's about has heroic as a picture of warrior tending a hay stack or a wizard eating breakfast, half-awake before his first coffee. That's not an imagery I associate with heroic tales. Entertaining a bunch of level 1 peasants in a tavern... well, that's a tale to be told! Let's throw him a copper piece for his performance. I disagree with your assessment on the appropriateness for D&D fantasy, especially to provide an inspiring image for a character class.
 

log in or register to remove this ad

Loved the Conan ones so much I decided to give the old Warhammer dwarf a go. They turned out pretty good. Same iterated art style prompt only the figure is switched to "dwarf with a bright red mohawk and massive beard." I know it's not canon with the slayer hair and wearing armor and all, but I don't care. I've always loved that look.

View attachment 404868
View attachment 404869View attachment 404870View attachment 404871
These look amazing. Makes me want to run a dwarf warrior as my next PC.
 

We do the same trick, only when the Reduced item is un-reduced it's usually way too heavy to hold or carry; you have to let go of it, meaning it has long since fallen out of range by the time you can resolve an Enlarge. (spells take measurable time to cast in our game)

Still a great way to sink ships, though - drop a large anvil from 500 feet and the decks/hulls of most ships are gonna have a hard time stopping it.

Noted. Actually our DM accepted that the loss of concentration on Reduce took effect at the time the Enlarge was taking effect, not at the start of the casting of the spell.

I was actually needed to sink a ship and didn't connect the idea. I can see it doing great in Dropping Anvils: The Nautical Remake.
 

Some heretics even blend drawing and photoshop. ;)

Zounds! What devilry is this?! It's kids playing with the calculation box instead of learning a proper craft like their fathers and grandfathers before them! Quit playing videogames and go create your own paint!

There's a LOT that can be done by mixing hand made work with AI assisted touch ups and AI added elements, back and forth, as just another piece of the process.

You can also just be the 'polaroid snapshot' equivalent and type in 'give me my stuff' and get some 'basic pics'.

People will learn to split the difference between art and 'quickie pieces' and things will move on.

There is actually an economic study (of debatable quality) that noticed that while generative AI dropped the average price of commission, the price lowering met a logically much larger demand, and the commission market actually grew overall since the introduction of generative AI. It needs confirmation, especially since I think it's too early to draw any conclusion.
 
Last edited:

I assume people will still appreciate human art. But I wonder what will happen when AI is genuinely artistic.

It might happen after the time when AI is sentient or self-aware, which will be much more worrisome.

Right now, I think it can't be artistic, but nothing preclude anyone to have an artistic image in his head, and generate an image of it with AI. The AI isn't able to produce something if asked to produce art, but it is just rendering what the human asks it for. If it is some uninspired and tired image of a girl with big assets in chainmail bikini, it probably won't be artistic. But nothing prevents one for asking for the druid drowning a gnoll in an... overgrown vegetable patch.
 
Last edited:

We like fantasy, but I've found that models tend to be quite good with more recent styles.

1746569161605.png



1746569767670.png


4o and Seedream, both with the following prompt:

A 1950s police station office, lit by soft daylight filtering through venetian blinds. A stocky middle-aged detective sits casually behind a wooden desk, his feet propped up on the tabletop. He wears a white shirt with rolled-up sleeves, dark suspenders, a loosely knotted tie, and a light-colored jacket draped over the back of his chair. He looks at the woman while smoking a cigar with smoke curling upward. He has a fedora tilted slightly back on his head. Across from him, a young woman sits upright in a simple wooden chair. She's dressed in 1950s attire: a modest dark dress with short sleeves, gloves in her lap, and a small pillbox hat, styled hair. She looks concerned. On the wall, a bulletin board with pinned papers. On the desk, a black rotary phone and scattered folders.

The second one is closer to the image I have in mind.
 

I mean capable of agency and creativity like a human.

That's what I wondered. At that point it runs into the general problem of hom sap trying to coexist with entities that are by moral standards, worth the same considerations as us, but are on the whole, as good or better at everything we are. Art won't be a standout then.
 

That's what I wondered. At that point it runs into the general problem of hom sap trying to coexist with entities that are by moral standards, worth the same considerations as us, but are on the whole, as good or better at everything we are. Art won't be a standout then.
Just because there is agency, doesnt necessarily mean there is a consciousness there experiencing the computer processing. They might still be toasters and telephones, even if complex.
 


I don't personally believe you can separate those two the way you're trying to there.
If there is an intricate pattern of dominoes knocking the next one down, there is never any consciousness there, no matter how intricate and interactive the patterns.

The circuitry today is incapable of consciousness. (Unless animism is true, and rocks and rivers are also conscious.) The material of the brain functions in ways that make consciousness possible, and ways that electronic circuitry cannot.
 

Into the Woods

Remove ads

Top